mlsanityData to 7 Oct 2026

Aortic root landmark localization with optimal transport loss for heatmap regression

arXiv 2407.04921 ↗First posted 6 Jul 2024cs.CV cs.AI stat.APcited by 0

Not on the map. Why?

Abstract (arXiv)

Anatomical landmark localization is gaining attention to ease the burden on physicians. Focusing on aortic root landmark localization, the three hinge points of the aortic valve can reduce the burden by automatically determining the valve size required for transcatheter aortic valve implantation surgery. Existing methods for landmark prediction of the aortic root mainly use time-consuming two-step estimation methods. We propose a highly accurate one-step landmark localization method from even coarse images. The proposed method uses an optimal transport loss to break the trade-off between prediction precision and learning stability in conventional heatmap regression methods. We apply the proposed method to the 3D CT image dataset collected at Sendai Kousei Hospital and show that it significantly improves the estimation error over existing methods and other loss functions. Our code is available on GitHub.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 32 of its 95 references that are in the map. First posted on arXiv 6 Jul 2024.

Builds on

32 of 95 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2022Generative Adversarial Networkscited by 5,603
  5. 2017Improved Training of Wasserstein GANscited by 2,223
  6. 2015Deep Reinforcement Learning with Double Q-learningcited by 1,704
  7. 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,518
  8. 2021Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentationcited by 1,218
  9. 2015Dueling Network Architectures for Deep Reinforcement Learningcited by 769
  10. 2018Computational Optimal Transportcited by 765
  11. 2017Wasserstein GANcited by 635
  12. 2019MultiResUNet : Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentationcited by 195
20 more
  1. 2020Rethinking the Heatmap Regression for Bottom-up Human Pose Estimationcited by 69
  2. 2019Why ResNet Works? Residuals Generalizecited by 39
  3. 2020Achieving robustness in classification using optimal transport with hinge regularizationcited by 27
  4. 2023ACC-UNet: A Completely Convolutional UNet model for the 2020scited by 26
  5. 2021Two-Stage Mesh Deep Learning for Automated Tooth Segmentation and Landmark Localization on 3D Intraoral Scanscited by 23
  6. 2020Deep Learning-Based Regression and Classification for Automatic Landmark Localization in Medical Imagescited by 22
  7. 2021Modality specific U-Net variants for biomedical image segmentation: A surveycited by 20
  8. 2019The Wasserstein-Fourier Distance for Stationary Time Seriescited by 18
  9. 2019KNEEL: Knee Anatomical Landmark Localization Using Hourglass Networkscited by 14
  10. 2021Sharp U-Net: Depthwise Convolutional Network for Biomedical Image Segmentationcited by 12
  11. 2020Volumetric landmark detection with a multi-scale shift equivariant neural networkcited by 9
  12. 2021Unsupervised Landmark Detection Based Spatiotemporal Motion Estimation for 4D Dynamic Medical Imagescited by 9
  13. 2021WOOD: Wasserstein-based Out-of-Distribution Detectioncited by 9
  14. 2018Partial Policy-based Reinforcement Learning for Anatomical Landmark Localization in 3D Medical Imagescited by 6
  15. 2020Contour Transformer Network for One-shot Segmentation of Anatomical Structurescited by 6
  16. 2021Learn Fine-grained Adaptive Loss for Multiple Anatomical Landmark Detection in Medical Imagescited by 6
  17. 2023Uniform-in-Time Wasserstein Stability Bounds for (Noisy) Stochastic Gradient Descentcited by 6
  18. 2020Region Proposal Network with Graph Prior and IoU-Balance Loss for Landmark Detection in 3D Ultrasoundcited by 5
  19. 2021Structure-Aware Long Short-Term Memory Network for 3D Cephalometric Landmark Detectioncited by 2
  20. 2021Facial Anatomical Landmark Detection using Regularized Transfer Learning with Application to Fetal Alcohol Syndrome Recognitioncited by 2

Built on by

Not cited yet.